python极其简单的爬虫妹子图

1、目标网站地址：http://sc.chinaz.com/tupian/meinvtupian.html

2、分析第2页的url：

3、源码展示：

from lxml import etree
import requests
import urllib.request
imgs = []

#获取图片列表
def getAllsrc(url):
    res = requests.get(url)
    html = etree.HTML(res.text)
    result = html.xpath('//a[@target="_blank"]/img')
    for temp in result:
        img = temp.attrib.values()[0];
        imgs.append(img)

#下载图片-urllib.request-
def downlocal():
    num = 0
    path = "D:/Temp/images/"
    for imgurl in imgs:
        num += 1
        print("正在下载第 "+str(num)+" 个图像")
        try:
            urllib.request.urlretrieve(imgurl, '{0}{1}.jpg'.format(path, num))  # 打开imgList,下载图片到本地
        except BaseException:
            pass
    print('图片下载完成，注意查看文件夹')

#这个太慢了
def downlocal2():
    num = 0
    for imgurl in imgs:
        num += 1
        path = "D:/Temp/images/"+str(num)+'.jpg'
        r = requests.get(imgurl)
        try:
            with open(path,'wb') as f:
                f.write(r.content)
                print("正在下载第 "+str(num)+" 张图")
        except BaseException:
            pass
    print('图片下载完成，注意查看文件夹')

#主入口
if __name__ == "__main__":
    for i in range(68):
        if(i==0):
            tempsrc = 'http://sc.chinaz.com/tupian/meinvtupian.html'
        else:
            tempsrc = 'http://sc.chinaz.com/tupian/meinvtupian_'+str(i)+'.html'
        i += 1;
        getAllsrc(tempsrc)

    #调用
    downlocal()

4、效果图：

来源：CSDN

作者：一眼泥沙

链接：https://blog.csdn.net/weixin_43386443/article/details/103586714